Skip to main content
Glama
parallelix-mcp

parallelix-mcp

Official

parallelix-mcp

An MCP (Model Context Protocol) server for the ParalleliX Compute API. It gives an MCP client (Claude Code, Claude Desktop) tools to offload parallel inference sub-tasks to the ParalleliX network, paid in $PRLX credits.

The pattern: your frontier agent orchestrates and reasons; the distributed open-source fleet runs the cheap, embarrassingly-parallel parts. Bulk classify, extract, summarize, or translate hundreds of items in one parallel_map call instead of burning frontier tokens on a loop.

What you need

  1. An API key. Create one in the ParalleliX app under Developers (connect a wallet, add $PRLX credits, create a key). The key looks like pk_live_… and is shown once.

  2. Node 18 or newer.

Related MCP server: Local AI MCP

Tools

  • parallel_map(items, instruction, model?) Run the same instruction over many items in parallel across the network. Returns one result per item with a Proof-of-Execution hash.

  • infer(prompt, model?) Run a single prompt on the network. Returns the completion, the serving node id, and its PoE hash.

  • network_status() List the models the network currently serves.

  • usage() Show this key's request count, $PRLX credits spent, and remaining balance.

Use with Claude Desktop

Add this to claude_desktop_config.json:

{
  "mcpServers": {
    "parallelix": {
      "command": "npx",
      "args": ["-y", "parallelix-mcp"],
      "env": {
        "PARALLELIX_API_KEY": "pk_live_your_key_here"
      }
    }
  }
}

Use with Claude Code

claude mcp add parallelix --env PARALLELIX_API_KEY=pk_live_your_key_here -- npx -y parallelix-mcp

Configuration

Env var

Required

Default

Notes

PARALLELIX_API_KEY

yes

none

Your pk_live_… key.

PARALLELIX_BASE_URL

no

https://api.parallelix.io

Point at a local coordinator for testing.

Honest notes

  • The network runs open-source models (currently 7B-class, e.g. qwen2.5:7b). It is not a frontier model and is not meant to replace one. It is a cheap parallel executor for bulk independent sub-tasks.

  • Capacity is real and finite. Large batches queue; usage and network_status show you what's available.

  • Credits are metered off-chain by the coordinator (deposit $PRLX once on-chain, no per-call gas). v1 is custodial.

License

MIT

Available Tools

4 tools
inferA

Run a single prompt on the ParalleliX network. Returns the completion plus the serving node id and Proof-of-Execution hash. For bulk independent work, prefer parallel_map.

Inputs: prompt (required), model.

network_statusB

List the models the ParalleliX network currently serves.

Inputs: no named parameters.

parallel_mapA

Run the SAME instruction over MANY items in parallel on the ParalleliX network. Ideal for bulk classify / extract / summarize / translate where each item is independent. Returns one result per item with a Proof-of-Execution hash. Use this instead of looping single calls: it fans out across the network's nodes simultaneously.

Inputs: items (required), instruction (required), model.

usageA

Show this API key's request count, $PRLX credits spent, and remaining credit balance.

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 4 tools

    Disambiguation5/5

    Each tool serves a distinct purpose: infer for single prompts, parallel_map for bulk, network_status for model info, usage for account info. No overlap.

    Naming Consistency5/5

    All tool names follow the same lowercase_with_underscores pattern (infer, network_status, parallel_map, usage), providing a predictable and clean interface.

    Tool Count5/5

    Four tools is perfectly scoped for a focused API wrapping inference, network info, and usage. Each tool is necessary and there are no redundant ones.

    Completeness4/5

    Covers the essential operations: single inference, bulk inference, network status, and usage. Minor gap: no explicit model selection parameter in infer/parallel_map, but it may be handled elsewhere.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      D
      maintenance
      An MCP server that enables users to query, compare, and synthesize responses from multiple local and cloud LLMs simultaneously using existing subscriptions. It provides tools for parallel model evaluation, consensus polling with an LLM-as-judge, and response synthesis across different model providers.
      8
      59 npm
      15
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Unified MCP server for managing local model runtimes (Ollama, LM Studio, etc.), enabling provider-agnostic discovery, lifecycle management, hardware-fit checks, and delegated inference.
      22
      104 npm
      Creative Commons Attribution Non Commercial No Derivatives 4.0 International